2

VPU: A Video-Based Point Cloud Upsampling Framework
In this work, we propose a new patch-based framework called VPU for the video-based point cloud upsampling task by effectively …
Kaisiyuan Wang,, Lu Sheng, Shuhang Gu,, Dong Xu
Cite Project DOI
Sequential Point Cloud Upsampling by Exploiting Multi-Scale Temporal Dependency
In this work, we propose a new sequential point cloud upsampling method called SPU, which aims to upsample sparse, non-uniform, and …
Kaisiyuan Wang,, Lu Sheng, Shuhang Gu,, Dong Xu
Cite Project DOI
Transformer3D-Det: Improving 3D Object Detection by Vote Refinement
Voting-based methods (e.g., VoteNet) have achieved promising results for 3D object detection. However, the simple voting operation in …
Lichen Zhao, Jinyang Guo,, Dong Xu, Lu Sheng
Cite Project DOI
Motion Compensated Virtual View Synthesis Using Novel Particle Cell
Due to the wide interest in advanced multimedia experience, free-viewpoint communication is being greatly developed in recent years. In …
Chi Ho Cheung, Lu Sheng, King Ngi Ngan
Cite DOI
PCG-TAL: Progressive Cross-Granularity Cooperation for Temporal Action Localization
There are two major lines of works, i.e., anchor-based and frame-based approaches, in the field of temporal action localization. But …
Rui Su, Dong Xu, Lu Sheng, Wanli Ouyang
Cite DOI
High-Quality Video Generation from Static Structural Annotations
This paper proposes a novel unsupervised video generation that is conditioned on a single structural annotation map, which in contrast …
Lu Sheng, Junting Pan, Jiaming Guo, Jing Shao, Chen Change Loy
Cite Code Project DOI
High-Quality Video Generation from Static Structural Annotations
Bags of tricks for learning depth and camera motion from monocular videos
  • Background: Based on the seminal work proposed by Zhou et al., much of the recent progress in learning monocular visual odometry, i. …
Bowen Dong, Lu Sheng
Cite Project DOI
Cascaded regression using landmark displacement for 3D face reconstruction
This paper proposes a novel model fitting algorithm for 3D facial expression reconstruction from a single image. Face expression …
Fanzi Wu, Songnan Li, Tianhao Zhao, King Ngi Ngan, Lu Sheng
Cite Project DOI
Visibility Constrained Generative Model for Depth-Based 3D Facial Pose Tracking
In this paper, we propose a generative framework that unifies depth-based 3D facial pose tracking and face model adaptation on-the-fly, …
Lu Sheng, Jianfei Cai, Tat-Jen Cham, Vladimir Pavlovic, King Ngi Ngan
Cite Project DOI
Visibility Constrained Generative Model for Depth-Based 3D Facial Pose Tracking
Spatio-Temporal Disocclusion Filling Using Novel Sprite Cells
Depth image-based rendering is an important technique for virtual view synthesis with limited 3-D data. However, occluded areas result …
Chi Ho Cheung, King Ngi Ngan, Lu Sheng
Cite DOI